DINOv2: Learning Robust Visual Features without Supervision

Tricks applied to DINO and iBOT to learn robust/generic features for many downstream tasks

My summary on HFPapers: https://huggingface.co/papers/2304.07193#64f81a7f35a0a9fc54363373
arXiv: https://arxiv.org/abs/2304.07193
Demo: https://dinov2.metademolab.com/

#arXiv #PaperThread #FoundationModels

LidarCLIP or: How I Learned to Talk to Point Clouds

Align LiDAR encoder to CLIP image encoder and you can query LiDAR through image similarity or even text.

My summary on HFPapers: https://huggingface.co/papers/2212.06858#64f6f05910a91217c38874b7
arXiv: https://arxiv.org/abs/2212.06858
PWC: https://paperswithcode.com/paper/lidarclip-or-how-i-learned-to-talk-to-point

#arXiv #PaperThread #FoundationModels

T'S PAPER DAY!

Seidel & Prinoth et al. has just been accepted for publication in A&A and you can find it on arXiv already today: https://arxiv.org/abs/2308.13622 ✨

Let us tell you a bit more 👇🏼🧵

@JuliaVSeidel

#PaperThread #paper #exoplanets #observations #publication

Hello, world!

Look, it's me 👀 My second first-author paper has just been accepted for publication in A&A and you can find it on arXiv already today ✨

Let me tell you a bit about it 👇🏼🧵

(okay a lot, it's a big kid)

https://arxiv.org/abs/2308.04523

#thread #PaperThread #astrodon #astronomy #observations

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Top-view and ground-view images can make neural maps that aid visual positioning.

My summary on HFPapers: https://huggingface.co/papers/2306.05407#64c3fcb171947b03ffcf314c
arXiv: https://arxiv.org/abs/2306.05407
PapersWithCode: https://paperswithcode.com/paper/snap-self-supervised-neural-maps-for-visual

#arXiv #PaperThread #NewPaper #SSL

Diffusion Models Beat GANs on Image Classification

Extract features (activations) at a block at a diffusion time step gives a decent classifier.

My summary on HFPapers: https://huggingface.co/papers/2307.08702#64c3fb7ebf1103bae84618a6

arXiv: https://arxiv.org/abs/2307.08702

Links: [PapersWithCode](https://paperswithcode.com/paper/diffusion-models-beat-gans-on-image)

#arxiv #NewPaper #PaperThread #sd

How is ChatGPT's behavior changing over time?

Monitors trends in performance of GPT-4 and GPT-3.5 (backend LLMs of ChatGPT) from March 2023 to June 2023 on diverse tasks.

My summary on HFPapers: https://huggingface.co/papers/2307.09009#64c3f9c2979493279b41df28
arXiv: https://arxiv.org/abs/2307.09009
GitHub: https://github.com/lchen001/LLMDrift

#arxiv #NewPaper #PaperThread #llm

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

Adding a fingerprint in the content and decoding to retrieve that fingerprint.

My summary on HFPapers: https://huggingface.co/papers/2306.04744#64ba95a7838da64e69080415

Links: [PapersWithCode](https://paperswithcode.com/paper/wouaf-weight-modulation-for-user-attribution), [website](https://wouaf.vercel.app/), [HuggingFace Space](https://huggingface.co/spaces/mpatel57/WOUAF-Text-to-Image), [Related - C2PA](https://c2pa.org/)

#arxiv #NewPaper #PaperThread #diffusion

LightGlue: Local Feature Matching at Light Speed

Improving SuperGlue with changes to transformer (GNN matching). Iterative design gives speed boost.

My summary on HFPapers: https://huggingface.co/papers/2306.13643#64ba93f75e13c0d8659b4ce8

Links: [PapersWithCode](https://paperswithcode.com/paper/lightglue-local-feature-matching-at-light), [GitHub](https://github.com/cvg/lightglue), [arxiv](https://arxiv.org/abs/2306.13643)

#lfm #arxiv #PaperThread #NewPaper #gnn

Llama 2: Open Foundation and Fine-Tuned Chat Models

Improving LLaMA with hacks.
Gotta admit (being a critic of Meta) they have tested it well.

HFPapers: https://huggingface.co/papers/2307.09288
My summary: https://huggingface.co/papers/2307.09288#64b79ed1104e7af01c0c6425

Links: [website](https://ai.meta.com/llama/), [Meta AI blog post](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/), [arxiv](https://arxiv.org/abs/2307.09288), [Meta news](https://about.fb.com/news/2023/07/llama-2/), [GitHub](https://github.com/facebookresearch/llama) ([Older LLaMA - v1](https://github.com/facebookresearch/llama/tree/llama_v1))

#NewPaper #PaperThread #arxiv #llm

SketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling

An exciting mix of Pix2Pix, PIFu (SDF generation), and mesh refinement hacks to create a facial mesh from interactive sketching.

@_akhaliq tweet: https://twitter.com/_akhaliq/status/1676090852697841664

My summary post on HFPapers: https://huggingface.co/papers/2307.00804#64b79817b5d293ec95a50f13

arXiv: https://arxiv.org/abs/2307.00804

GitHub: https://github.com/zhongjinluo/SketchMetaFace

#NewPaper #PaperThread #arxiv

AI systems fail to generalize to novel environments, that differ from their training environment. Crucially, they are vulnerable to spurious correlations.

To facilitate progress, we introduce Spawrious 🐾, a benchmark suite for robustness/OOD/domain generalization algorithms.

- Paper link https://arxiv.org/abs/2303.05470

#PaperThread [1/7]

#ai #NewPaper #arxiv #CV #genAI #machinelearning #artificialintelligence

One can't judge a click model only by how well it ranks documents, we also need to make sure it actively identified and removed biases hidden in the logged data.

That's what we showed in our recent #SIGIR23 paper with Philipp Hager, Jean-Michel Renders and Maarten de Rijke.

https://arxiv.org/abs/2304.09560

#PaperThread #ULTR #ClickModels #IR

Is this really me catching up to TODAY?

For the fifth paper of my #MonthOfArXiv (IT’S FROM TODAY!!), I chose a paper studying the planet MASCARA-4 b. If you are intrigued by that name, I recommend reading yesterday’s thread about MASCARA-1 b.

The title of the paper is “Detection of rubidium and samarium in the atmosphere of the ultra-hot Jupiter MASCARA-4 b” and was written by Jiang and collaborators.

Let’s check it out! 👇🏼🧵

🔗 https://arxiv.org/abs/2304.04948

#challenge #PaperThread

For the forth paper of my #MonthOfArXiv (catching up from yesterday again), I chose a paper studying the upper atmospheres of a couplet of planets.

The title of the paper is “Characterisation of the upper atmospheres of HAT-P-32 b, WASP-69 b, GJ 1214 b, and WASP-76 b through their He I triplet absorption” and was written by Lampón and collaborators.

Let’s dive right into it! 👇🏼🧵

🔗 https://arxiv.org/abs/2304.03839

#challenge #PaperThread

I have been reading two papers today that I will share in a #PaperThread after dinner. Stay tuned to read about helium and samarium 🤓

** checks where samarium is on the periodic table 🫣 **

Paper No. 2 for today!

For the third paper of my #MonthOfArXiv I have chosen a paper from my own field. I hope that I can give you a personal flavour, because it is about an important mechanism. Hooked? Follow me! 👇🏼🧵

The title of the paper is “The PEPSI Exoplanet Transit Survey. III: The detection of Fe I, Cr I and Ti I in the atmosphere of MASCARA-1 b through high-resolution emission spectroscopy” and was written by Scandariato et al.

🔗 https://arxiv.org/abs/2304.03328

#challenge #PaperThread

For the second paper in my #MonthOfArXiv, I read a paper that is again not really in my field, but I just love reading about Hycean Worlds, maybe because I can somehow picture them? 🤔

The title of today’s first paper (originally from Friday) is “The Runaway Greenhouse Effect on Hycean Worlds” and it is written by Hamish Innes, Shang-Min Tsai and Raymond T. Pierrehumbert.

What is a Hycean world, you wonder? Well, let’s find out together! 👇🏼🧵

🔗 https://arxiv.org/abs/2304.02698

#challenge #PaperThread

And this was it, everyone! I hope you enjoyed this little #PaperThread about "G 68-34: A Double-Lined M-Dwarf Eclipsing Binary in a Hierarchical Triple System" by Pass&Charbonneau, 2023.

I really loved reading this paper, even though I was a bit worried I wouldn't understand a thing...

A double-lined M-dwarf eclipsing binary doesn't sound so scary anymore, does it? 😇

So let's get this party started!

For the first paper in my #MonthOfArXiv, I decided to go a little wild: I picked a paper that isn't really in my research field. Why not start this challenge with a real challenge?

The title of the paper is "G 68-34: A Double-Lined M-Dwarf Eclipsing Binary in a Hierarchical Triple System" and it is written by Emily K. Pass and David Charbonneau.

A double-lined M-dw... what? Well, let's get into this! 👇🏼🧵

🔗 https://arxiv.org/abs/2304.02466

#challenge #PaperThread